#include <linux/cpufreq.h>
#include "i915_drv.h"
#include "intel_drv.h"
+#include "../../../platform/x86/intel_ips.h"
+#include <linux/module.h>
/* FBC, or Frame Buffer Compression, is a technique employed to compress the
* framebuffer contents in-memory, aiming at reducing the required bandwidth
* i915.i915_enable_fbc parameter
*/
-void i8xx_disable_fbc(struct drm_device *dev)
+static void i8xx_disable_fbc(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
u32 fbc_ctl;
DRM_DEBUG_KMS("disabled FBC\n");
}
-void i8xx_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
+static void i8xx_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
{
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
cfb_pitch, crtc->y, intel_crtc->plane);
}
-bool i8xx_fbc_enabled(struct drm_device *dev)
+static bool i8xx_fbc_enabled(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
return I915_READ(FBC_CONTROL) & FBC_CTL_EN;
}
-void g4x_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
+static void g4x_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
{
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
DRM_DEBUG_KMS("enabled fbc on plane %d\n", intel_crtc->plane);
}
-void g4x_disable_fbc(struct drm_device *dev)
+static void g4x_disable_fbc(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
u32 dpfc_ctl;
}
}
-bool g4x_fbc_enabled(struct drm_device *dev)
+static bool g4x_fbc_enabled(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
gen6_gt_force_wake_put(dev_priv);
}
-void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
+static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
{
struct drm_device *dev = crtc->dev;
struct drm_i915_private *dev_priv = dev->dev_private;
DRM_DEBUG_KMS("enabled fbc on plane %d\n", intel_crtc->plane);
}
-void ironlake_disable_fbc(struct drm_device *dev)
+static void ironlake_disable_fbc(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
u32 dpfc_ctl;
}
}
-bool ironlake_fbc_enabled(struct drm_device *dev)
+static bool ironlake_fbc_enabled(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
* - going to an unsupported config (interlace, pixel multiply, etc.)
*/
list_for_each_entry(tmp_crtc, &dev->mode_config.crtc_list, head) {
- if (tmp_crtc->enabled && tmp_crtc->fb) {
+ if (tmp_crtc->enabled &&
+ !to_intel_crtc(tmp_crtc)->primary_disabled &&
+ tmp_crtc->fb) {
if (crtc) {
DRM_DEBUG_KMS("more than one pipe active, disabling compression\n");
dev_priv->no_fbc_reason = FBC_MULTIPLE_PIPES;
}
}
+static void i915_pineview_get_mem_freq(struct drm_device *dev)
+{
+ drm_i915_private_t *dev_priv = dev->dev_private;
+ u32 tmp;
+
+ tmp = I915_READ(CLKCFG);
+
+ switch (tmp & CLKCFG_FSB_MASK) {
+ case CLKCFG_FSB_533:
+ dev_priv->fsb_freq = 533; /* 133*4 */
+ break;
+ case CLKCFG_FSB_800:
+ dev_priv->fsb_freq = 800; /* 200*4 */
+ break;
+ case CLKCFG_FSB_667:
+ dev_priv->fsb_freq = 667; /* 167*4 */
+ break;
+ case CLKCFG_FSB_400:
+ dev_priv->fsb_freq = 400; /* 100*4 */
+ break;
+ }
+
+ switch (tmp & CLKCFG_MEM_MASK) {
+ case CLKCFG_MEM_533:
+ dev_priv->mem_freq = 533;
+ break;
+ case CLKCFG_MEM_667:
+ dev_priv->mem_freq = 667;
+ break;
+ case CLKCFG_MEM_800:
+ dev_priv->mem_freq = 800;
+ break;
+ }
+
+ /* detect pineview DDR3 setting */
+ tmp = I915_READ(CSHRDDR3CTL);
+ dev_priv->is_ddr3 = (tmp & CSHRDDR3CTL_DDR3) ? 1 : 0;
+}
+
+static void i915_ironlake_get_mem_freq(struct drm_device *dev)
+{
+ drm_i915_private_t *dev_priv = dev->dev_private;
+ u16 ddrpll, csipll;
+
+ ddrpll = I915_READ16(DDRMPLL1);
+ csipll = I915_READ16(CSIPLL0);
+
+ switch (ddrpll & 0xff) {
+ case 0xc:
+ dev_priv->mem_freq = 800;
+ break;
+ case 0x10:
+ dev_priv->mem_freq = 1066;
+ break;
+ case 0x14:
+ dev_priv->mem_freq = 1333;
+ break;
+ case 0x18:
+ dev_priv->mem_freq = 1600;
+ break;
+ default:
+ DRM_DEBUG_DRIVER("unknown memory frequency 0x%02x\n",
+ ddrpll & 0xff);
+ dev_priv->mem_freq = 0;
+ break;
+ }
+
+ dev_priv->r_t = dev_priv->mem_freq;
+
+ switch (csipll & 0x3ff) {
+ case 0x00c:
+ dev_priv->fsb_freq = 3200;
+ break;
+ case 0x00e:
+ dev_priv->fsb_freq = 3733;
+ break;
+ case 0x010:
+ dev_priv->fsb_freq = 4266;
+ break;
+ case 0x012:
+ dev_priv->fsb_freq = 4800;
+ break;
+ case 0x014:
+ dev_priv->fsb_freq = 5333;
+ break;
+ case 0x016:
+ dev_priv->fsb_freq = 5866;
+ break;
+ case 0x018:
+ dev_priv->fsb_freq = 6400;
+ break;
+ default:
+ DRM_DEBUG_DRIVER("unknown fsb frequency 0x%04x\n",
+ csipll & 0x3ff);
+ dev_priv->fsb_freq = 0;
+ break;
+ }
+
+ if (dev_priv->fsb_freq == 3200) {
+ dev_priv->c_m = 0;
+ } else if (dev_priv->fsb_freq > 3200 && dev_priv->fsb_freq <= 4800) {
+ dev_priv->c_m = 1;
+ } else {
+ dev_priv->c_m = 2;
+ }
+}
+
static const struct cxsr_latency cxsr_latency_table[] = {
{1, 0, 800, 400, 3382, 33382, 3983, 33983}, /* DDR2-400 SC */
{1, 0, 800, 667, 3354, 33354, 3807, 33807}, /* DDR2-667 SC */
{0, 1, 400, 800, 6042, 36042, 6584, 36584}, /* DDR3-800 SC */
};
-const struct cxsr_latency *intel_get_cxsr_latency(int is_desktop,
+static const struct cxsr_latency *intel_get_cxsr_latency(int is_desktop,
int is_ddr3,
int fsb,
int mem)
return NULL;
}
-void pineview_disable_cxsr(struct drm_device *dev)
+static void pineview_disable_cxsr(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
*/
static const int latency_ns = 5000;
-int i9xx_get_fifo_size(struct drm_device *dev, int plane)
+static int i9xx_get_fifo_size(struct drm_device *dev, int plane)
{
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t dsparb = I915_READ(DSPARB);
return size;
}
-int i85x_get_fifo_size(struct drm_device *dev, int plane)
+static int i85x_get_fifo_size(struct drm_device *dev, int plane)
{
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t dsparb = I915_READ(DSPARB);
return size;
}
-int i845_get_fifo_size(struct drm_device *dev, int plane)
+static int i845_get_fifo_size(struct drm_device *dev, int plane)
{
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t dsparb = I915_READ(DSPARB);
return size;
}
-int i830_get_fifo_size(struct drm_device *dev, int plane)
+static int i830_get_fifo_size(struct drm_device *dev, int plane)
{
struct drm_i915_private *dev_priv = dev->dev_private;
uint32_t dsparb = I915_READ(DSPARB);
return enabled;
}
-void pineview_update_wm(struct drm_device *dev)
+static void pineview_update_wm(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_crtc *crtc;
#define single_plane_enabled(mask) is_power_of_2(mask)
-void valleyview_update_wm(struct drm_device *dev)
+static void valleyview_update_wm(struct drm_device *dev)
{
static const int sr_latency_ns = 12000;
struct drm_i915_private *dev_priv = dev->dev_private;
(I915_READ(DSPFW3) | (cursor_sr << DSPFW_CURSOR_SR_SHIFT)));
}
-void g4x_update_wm(struct drm_device *dev)
+static void g4x_update_wm(struct drm_device *dev)
{
static const int sr_latency_ns = 12000;
struct drm_i915_private *dev_priv = dev->dev_private;
(cursor_sr << DSPFW_CURSOR_SR_SHIFT));
}
-void i965_update_wm(struct drm_device *dev)
+static void i965_update_wm(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_crtc *crtc;
I915_WRITE(DSPFW3, (cursor_sr << DSPFW_CURSOR_SR_SHIFT));
}
-void i9xx_update_wm(struct drm_device *dev)
+static void i9xx_update_wm(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
const struct intel_watermark_params *wm_info;
}
}
-void i830_update_wm(struct drm_device *dev)
+static void i830_update_wm(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct drm_crtc *crtc;
display, cursor);
}
-void ironlake_update_wm(struct drm_device *dev)
+static void ironlake_update_wm(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
int fbc_wm, plane_wm, cursor_wm;
*/
}
-void sandybridge_update_wm(struct drm_device *dev)
+static void sandybridge_update_wm(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
int latency = SNB_READ_WM0_LATENCY() * 100; /* In unit 0.1us */
enabled |= 2;
}
- /* IVB has 3 pipes */
- if (IS_IVYBRIDGE(dev) &&
+ if ((dev_priv->num_pipe == 3) &&
g4x_compute_wm0(dev, 2,
&sandybridge_display_wm_info, latency,
&sandybridge_cursor_wm_info, latency,
cursor_wm);
}
+static void
+haswell_update_linetime_wm(struct drm_device *dev, int pipe,
+ struct drm_display_mode *mode)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 temp;
+
+ temp = I915_READ(PIPE_WM_LINETIME(pipe));
+ temp &= ~PIPE_WM_LINETIME_MASK;
+
+ /* The WM are computed with base on how long it takes to fill a single
+ * row at the given clock rate, multiplied by 8.
+ * */
+ temp |= PIPE_WM_LINETIME_TIME(
+ ((mode->crtc_hdisplay * 1000) / mode->clock) * 8);
+
+ /* IPS watermarks are only used by pipe A, and are ignored by
+ * pipes B and C. They are calculated similarly to the common
+ * linetime values, except that we are using CD clock frequency
+ * in MHz instead of pixel rate for the division.
+ *
+ * This is a placeholder for the IPS watermark calculation code.
+ */
+
+ I915_WRITE(PIPE_WM_LINETIME(pipe), temp);
+}
+
static bool
sandybridge_compute_sprite_wm(struct drm_device *dev, int plane,
uint32_t sprite_width, int pixel_size,
return *sprite_wm > 0x3ff ? false : true;
}
-void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
+static void sandybridge_update_sprite_wm(struct drm_device *dev, int pipe,
uint32_t sprite_width, int pixel_size)
{
struct drm_i915_private *dev_priv = dev->dev_private;
dev_priv->display.update_wm(dev);
}
+void intel_update_linetime_watermarks(struct drm_device *dev,
+ int pipe, struct drm_display_mode *mode)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ if (dev_priv->display.update_linetime_wm)
+ dev_priv->display.update_linetime_wm(dev, pipe, mode);
+}
+
void intel_update_sprite_watermarks(struct drm_device *dev, int pipe,
uint32_t sprite_width, int pixel_size)
{
void gen6_set_rps(struct drm_device *dev, u8 val)
{
struct drm_i915_private *dev_priv = dev->dev_private;
- u32 swreq;
+ u32 limits;
+
+ limits = 0;
+ if (val >= dev_priv->max_delay)
+ val = dev_priv->max_delay;
+ else
+ limits |= dev_priv->max_delay << 24;
+
+ if (val <= dev_priv->min_delay)
+ val = dev_priv->min_delay;
+ else
+ limits |= dev_priv->min_delay << 16;
+
+ if (val == dev_priv->cur_delay)
+ return;
- swreq = (val & 0x3ff) << 25;
- I915_WRITE(GEN6_RPNSWREQ, swreq);
+ I915_WRITE(GEN6_RPNSWREQ,
+ GEN6_FREQUENCY(val) |
+ GEN6_OFFSET(0) |
+ GEN6_AGGRESSIVE_TURBO);
+
+ /* Make sure we continue to get interrupts
+ * until we hit the minimum or maximum frequencies.
+ */
+ I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, limits);
+
+ dev_priv->cur_delay = val;
}
void gen6_disable_rps(struct drm_device *dev)
void gen6_enable_rps(struct drm_i915_private *dev_priv)
{
- u32 rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
- u32 gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
+ struct intel_ring_buffer *ring;
+ u32 rp_state_cap;
+ u32 gt_perf_status;
u32 pcu_mbox, rc6_mask = 0;
u32 gtfifodbg;
- int cur_freq, min_freq, max_freq;
int rc6_mode;
int i;
gen6_gt_force_wake_get(dev_priv);
+ rp_state_cap = I915_READ(GEN6_RP_STATE_CAP);
+ gt_perf_status = I915_READ(GEN6_GT_PERF_STATUS);
+
+ /* In units of 100MHz */
+ dev_priv->max_delay = rp_state_cap & 0xff;
+ dev_priv->min_delay = (rp_state_cap & 0xff0000) >> 16;
+ dev_priv->cur_delay = 0;
+
/* disable the counters and set deterministic thresholds */
I915_WRITE(GEN6_RC_CONTROL, 0);
I915_WRITE(GEN6_RC_EVALUATION_INTERVAL, 125000);
I915_WRITE(GEN6_RC_IDLE_HYSTERSIS, 25);
- for (i = 0; i < I915_NUM_RINGS; i++)
- I915_WRITE(RING_MAX_IDLE(dev_priv->ring[i].mmio_base), 10);
+ for_each_ring(ring, dev_priv, i)
+ I915_WRITE(RING_MAX_IDLE(ring->mmio_base), 10);
I915_WRITE(GEN6_RC_SLEEP, 0);
I915_WRITE(GEN6_RC1e_THRESHOLD, 1000);
I915_WRITE(GEN6_RP_DOWN_TIMEOUT, 1000000);
I915_WRITE(GEN6_RP_INTERRUPT_LIMITS,
- 18 << 24 |
- 6 << 16);
+ dev_priv->max_delay << 24 |
+ dev_priv->min_delay << 16);
I915_WRITE(GEN6_RP_UP_THRESHOLD, 10000);
I915_WRITE(GEN6_RP_DOWN_THRESHOLD, 1000000);
I915_WRITE(GEN6_RP_UP_EI, 100000);
I915_WRITE(GEN6_RP_IDLE_HYSTERSIS, 10);
I915_WRITE(GEN6_RP_CONTROL,
GEN6_RP_MEDIA_TURBO |
- GEN6_RP_MEDIA_HW_MODE |
+ GEN6_RP_MEDIA_HW_NORMAL_MODE |
GEN6_RP_MEDIA_IS_GFX |
GEN6_RP_ENABLE |
GEN6_RP_UP_BUSY_AVG |
500))
DRM_ERROR("timeout waiting for pcode mailbox to finish\n");
- min_freq = (rp_state_cap & 0xff0000) >> 16;
- max_freq = rp_state_cap & 0xff;
- cur_freq = (gt_perf_status & 0xff00) >> 8;
-
/* Check for overclock support */
if (wait_for((I915_READ(GEN6_PCODE_MAILBOX) & GEN6_PCODE_READY) == 0,
500))
500))
DRM_ERROR("timeout waiting for pcode mailbox to finish\n");
if (pcu_mbox & (1<<31)) { /* OC supported */
- max_freq = pcu_mbox & 0xff;
+ dev_priv->max_delay = pcu_mbox & 0xff;
DRM_DEBUG_DRIVER("overclocking supported, adjusting frequency max to %dMHz\n", pcu_mbox * 50);
}
- /* In units of 100MHz */
- dev_priv->max_delay = max_freq;
- dev_priv->min_delay = min_freq;
- dev_priv->cur_delay = cur_freq;
+ gen6_set_rps(dev_priv->dev, (gt_perf_status & 0xff00) >> 8);
/* requires MSI enabled */
I915_WRITE(GEN6_PMIER,
void ironlake_enable_rc6(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
+ struct intel_ring_buffer *ring = &dev_priv->ring[RCS];
int ret;
/* rc6 disabled by default due to repeated reports of hanging during
* GPU can automatically power down the render unit if given a page
* to save state.
*/
- ret = BEGIN_LP_RING(6);
+ ret = intel_ring_begin(ring, 6);
if (ret) {
ironlake_teardown_rc6(dev);
mutex_unlock(&dev->struct_mutex);
return;
}
- OUT_RING(MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
- OUT_RING(MI_SET_CONTEXT);
- OUT_RING(dev_priv->renderctx->gtt_offset |
- MI_MM_SPACE_GTT |
- MI_SAVE_EXT_STATE_EN |
- MI_RESTORE_EXT_STATE_EN |
- MI_RESTORE_INHIBIT);
- OUT_RING(MI_SUSPEND_FLUSH);
- OUT_RING(MI_NOOP);
- OUT_RING(MI_FLUSH);
- ADVANCE_LP_RING();
+ intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
+ intel_ring_emit(ring, MI_SET_CONTEXT);
+ intel_ring_emit(ring, dev_priv->renderctx->gtt_offset |
+ MI_MM_SPACE_GTT |
+ MI_SAVE_EXT_STATE_EN |
+ MI_RESTORE_EXT_STATE_EN |
+ MI_RESTORE_INHIBIT);
+ intel_ring_emit(ring, MI_SUSPEND_FLUSH);
+ intel_ring_emit(ring, MI_NOOP);
+ intel_ring_emit(ring, MI_FLUSH);
+ intel_ring_advance(ring);
/*
* Wait for the command parser to advance past MI_SET_CONTEXT. The HW
* does an implicit flush, combined with MI_FLUSH above, it should be
* safe to assume that renderctx is valid
*/
- ret = intel_wait_ring_idle(LP_RING(dev_priv));
+ ret = intel_wait_ring_idle(ring);
if (ret) {
DRM_ERROR("failed to enable ironlake power power savings\n");
ironlake_teardown_rc6(dev);
mutex_unlock(&dev->struct_mutex);
}
+static unsigned long intel_pxfreq(u32 vidfreq)
+{
+ unsigned long freq;
+ int div = (vidfreq & 0x3f0000) >> 16;
+ int post = (vidfreq & 0x3000) >> 12;
+ int pre = (vidfreq & 0x7);
+
+ if (!pre)
+ return 0;
+
+ freq = ((div * 133333) / ((1<<post) * pre));
+
+ return freq;
+}
+
+static const struct cparams {
+ u16 i;
+ u16 t;
+ u16 m;
+ u16 c;
+} cparams[] = {
+ { 1, 1333, 301, 28664 },
+ { 1, 1066, 294, 24460 },
+ { 1, 800, 294, 25192 },
+ { 0, 1333, 276, 27605 },
+ { 0, 1066, 276, 27605 },
+ { 0, 800, 231, 23784 },
+};
+
+unsigned long i915_chipset_val(struct drm_i915_private *dev_priv)
+{
+ u64 total_count, diff, ret;
+ u32 count1, count2, count3, m = 0, c = 0;
+ unsigned long now = jiffies_to_msecs(jiffies), diff1;
+ int i;
+
+ diff1 = now - dev_priv->last_time1;
+
+ /* Prevent division-by-zero if we are asking too fast.
+ * Also, we don't get interesting results if we are polling
+ * faster than once in 10ms, so just return the saved value
+ * in such cases.
+ */
+ if (diff1 <= 10)
+ return dev_priv->chipset_power;
+
+ count1 = I915_READ(DMIEC);
+ count2 = I915_READ(DDREC);
+ count3 = I915_READ(CSIEC);
+
+ total_count = count1 + count2 + count3;
+
+ /* FIXME: handle per-counter overflow */
+ if (total_count < dev_priv->last_count1) {
+ diff = ~0UL - dev_priv->last_count1;
+ diff += total_count;
+ } else {
+ diff = total_count - dev_priv->last_count1;
+ }
+
+ for (i = 0; i < ARRAY_SIZE(cparams); i++) {
+ if (cparams[i].i == dev_priv->c_m &&
+ cparams[i].t == dev_priv->r_t) {
+ m = cparams[i].m;
+ c = cparams[i].c;
+ break;
+ }
+ }
+
+ diff = div_u64(diff, diff1);
+ ret = ((m * diff) + c);
+ ret = div_u64(ret, 10);
+
+ dev_priv->last_count1 = total_count;
+ dev_priv->last_time1 = now;
+
+ dev_priv->chipset_power = ret;
+
+ return ret;
+}
+
+unsigned long i915_mch_val(struct drm_i915_private *dev_priv)
+{
+ unsigned long m, x, b;
+ u32 tsfs;
+
+ tsfs = I915_READ(TSFS);
+
+ m = ((tsfs & TSFS_SLOPE_MASK) >> TSFS_SLOPE_SHIFT);
+ x = I915_READ8(TR1);
+
+ b = tsfs & TSFS_INTR_MASK;
+
+ return ((m * x) / 127) - b;
+}
+
+static u16 pvid_to_extvid(struct drm_i915_private *dev_priv, u8 pxvid)
+{
+ static const struct v_table {
+ u16 vd; /* in .1 mil */
+ u16 vm; /* in .1 mil */
+ } v_table[] = {
+ { 0, 0, },
+ { 375, 0, },
+ { 500, 0, },
+ { 625, 0, },
+ { 750, 0, },
+ { 875, 0, },
+ { 1000, 0, },
+ { 1125, 0, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4125, 3000, },
+ { 4250, 3125, },
+ { 4375, 3250, },
+ { 4500, 3375, },
+ { 4625, 3500, },
+ { 4750, 3625, },
+ { 4875, 3750, },
+ { 5000, 3875, },
+ { 5125, 4000, },
+ { 5250, 4125, },
+ { 5375, 4250, },
+ { 5500, 4375, },
+ { 5625, 4500, },
+ { 5750, 4625, },
+ { 5875, 4750, },
+ { 6000, 4875, },
+ { 6125, 5000, },
+ { 6250, 5125, },
+ { 6375, 5250, },
+ { 6500, 5375, },
+ { 6625, 5500, },
+ { 6750, 5625, },
+ { 6875, 5750, },
+ { 7000, 5875, },
+ { 7125, 6000, },
+ { 7250, 6125, },
+ { 7375, 6250, },
+ { 7500, 6375, },
+ { 7625, 6500, },
+ { 7750, 6625, },
+ { 7875, 6750, },
+ { 8000, 6875, },
+ { 8125, 7000, },
+ { 8250, 7125, },
+ { 8375, 7250, },
+ { 8500, 7375, },
+ { 8625, 7500, },
+ { 8750, 7625, },
+ { 8875, 7750, },
+ { 9000, 7875, },
+ { 9125, 8000, },
+ { 9250, 8125, },
+ { 9375, 8250, },
+ { 9500, 8375, },
+ { 9625, 8500, },
+ { 9750, 8625, },
+ { 9875, 8750, },
+ { 10000, 8875, },
+ { 10125, 9000, },
+ { 10250, 9125, },
+ { 10375, 9250, },
+ { 10500, 9375, },
+ { 10625, 9500, },
+ { 10750, 9625, },
+ { 10875, 9750, },
+ { 11000, 9875, },
+ { 11125, 10000, },
+ { 11250, 10125, },
+ { 11375, 10250, },
+ { 11500, 10375, },
+ { 11625, 10500, },
+ { 11750, 10625, },
+ { 11875, 10750, },
+ { 12000, 10875, },
+ { 12125, 11000, },
+ { 12250, 11125, },
+ { 12375, 11250, },
+ { 12500, 11375, },
+ { 12625, 11500, },
+ { 12750, 11625, },
+ { 12875, 11750, },
+ { 13000, 11875, },
+ { 13125, 12000, },
+ { 13250, 12125, },
+ { 13375, 12250, },
+ { 13500, 12375, },
+ { 13625, 12500, },
+ { 13750, 12625, },
+ { 13875, 12750, },
+ { 14000, 12875, },
+ { 14125, 13000, },
+ { 14250, 13125, },
+ { 14375, 13250, },
+ { 14500, 13375, },
+ { 14625, 13500, },
+ { 14750, 13625, },
+ { 14875, 13750, },
+ { 15000, 13875, },
+ { 15125, 14000, },
+ { 15250, 14125, },
+ { 15375, 14250, },
+ { 15500, 14375, },
+ { 15625, 14500, },
+ { 15750, 14625, },
+ { 15875, 14750, },
+ { 16000, 14875, },
+ { 16125, 15000, },
+ };
+ if (dev_priv->info->is_mobile)
+ return v_table[pxvid].vm;
+ else
+ return v_table[pxvid].vd;
+}
+
+void i915_update_gfx_val(struct drm_i915_private *dev_priv)
+{
+ struct timespec now, diff1;
+ u64 diff;
+ unsigned long diffms;
+ u32 count;
+
+ if (dev_priv->info->gen != 5)
+ return;
+
+ getrawmonotonic(&now);
+ diff1 = timespec_sub(now, dev_priv->last_time2);
+
+ /* Don't divide by 0 */
+ diffms = diff1.tv_sec * 1000 + diff1.tv_nsec / 1000000;
+ if (!diffms)
+ return;
+
+ count = I915_READ(GFXEC);
+
+ if (count < dev_priv->last_count2) {
+ diff = ~0UL - dev_priv->last_count2;
+ diff += count;
+ } else {
+ diff = count - dev_priv->last_count2;
+ }
+
+ dev_priv->last_count2 = count;
+ dev_priv->last_time2 = now;
+
+ /* More magic constants... */
+ diff = diff * 1181;
+ diff = div_u64(diff, diffms * 10);
+ dev_priv->gfx_power = diff;
+}
+
+unsigned long i915_gfx_val(struct drm_i915_private *dev_priv)
+{
+ unsigned long t, corr, state1, corr2, state2;
+ u32 pxvid, ext_v;
+
+ pxvid = I915_READ(PXVFREQ_BASE + (dev_priv->cur_delay * 4));
+ pxvid = (pxvid >> 24) & 0x7f;
+ ext_v = pvid_to_extvid(dev_priv, pxvid);
+
+ state1 = ext_v;
+
+ t = i915_mch_val(dev_priv);
+
+ /* Revel in the empirically derived constants */
+
+ /* Correction factor in 1/100000 units */
+ if (t > 80)
+ corr = ((t * 2349) + 135940);
+ else if (t >= 50)
+ corr = ((t * 964) + 29317);
+ else /* < 50 */
+ corr = ((t * 301) + 1004);
+
+ corr = corr * ((150142 * state1) / 10000 - 78642);
+ corr /= 100000;
+ corr2 = (corr * dev_priv->corr);
+
+ state2 = (corr2 * state1) / 10000;
+ state2 /= 100; /* convert to mW */
+
+ i915_update_gfx_val(dev_priv);
+
+ return dev_priv->gfx_power + state2;
+}
+
+/* Global for IPS driver to get at the current i915 device */
+static struct drm_i915_private *i915_mch_dev;
+/*
+ * Lock protecting IPS related data structures
+ * - i915_mch_dev
+ * - dev_priv->max_delay
+ * - dev_priv->min_delay
+ * - dev_priv->fmax
+ * - dev_priv->gpu_busy
+ */
+static DEFINE_SPINLOCK(mchdev_lock);
+
+/**
+ * i915_read_mch_val - return value for IPS use
+ *
+ * Calculate and return a value for the IPS driver to use when deciding whether
+ * we have thermal and power headroom to increase CPU or GPU power budget.
+ */
+unsigned long i915_read_mch_val(void)
+{
+ struct drm_i915_private *dev_priv;
+ unsigned long chipset_val, graphics_val, ret = 0;
+
+ spin_lock(&mchdev_lock);
+ if (!i915_mch_dev)
+ goto out_unlock;
+ dev_priv = i915_mch_dev;
+
+ chipset_val = i915_chipset_val(dev_priv);
+ graphics_val = i915_gfx_val(dev_priv);
+
+ ret = chipset_val + graphics_val;
+
+out_unlock:
+ spin_unlock(&mchdev_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(i915_read_mch_val);
+
+/**
+ * i915_gpu_raise - raise GPU frequency limit
+ *
+ * Raise the limit; IPS indicates we have thermal headroom.
+ */
+bool i915_gpu_raise(void)
+{
+ struct drm_i915_private *dev_priv;
+ bool ret = true;
+
+ spin_lock(&mchdev_lock);
+ if (!i915_mch_dev) {
+ ret = false;
+ goto out_unlock;
+ }
+ dev_priv = i915_mch_dev;
+
+ if (dev_priv->max_delay > dev_priv->fmax)
+ dev_priv->max_delay--;
+
+out_unlock:
+ spin_unlock(&mchdev_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(i915_gpu_raise);
+
+/**
+ * i915_gpu_lower - lower GPU frequency limit
+ *
+ * IPS indicates we're close to a thermal limit, so throttle back the GPU
+ * frequency maximum.
+ */
+bool i915_gpu_lower(void)
+{
+ struct drm_i915_private *dev_priv;
+ bool ret = true;
+
+ spin_lock(&mchdev_lock);
+ if (!i915_mch_dev) {
+ ret = false;
+ goto out_unlock;
+ }
+ dev_priv = i915_mch_dev;
+
+ if (dev_priv->max_delay < dev_priv->min_delay)
+ dev_priv->max_delay++;
+
+out_unlock:
+ spin_unlock(&mchdev_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(i915_gpu_lower);
+
+/**
+ * i915_gpu_busy - indicate GPU business to IPS
+ *
+ * Tell the IPS driver whether or not the GPU is busy.
+ */
+bool i915_gpu_busy(void)
+{
+ struct drm_i915_private *dev_priv;
+ bool ret = false;
+
+ spin_lock(&mchdev_lock);
+ if (!i915_mch_dev)
+ goto out_unlock;
+ dev_priv = i915_mch_dev;
+
+ ret = dev_priv->busy;
+
+out_unlock:
+ spin_unlock(&mchdev_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(i915_gpu_busy);
+
+/**
+ * i915_gpu_turbo_disable - disable graphics turbo
+ *
+ * Disable graphics turbo by resetting the max frequency and setting the
+ * current frequency to the default.
+ */
+bool i915_gpu_turbo_disable(void)
+{
+ struct drm_i915_private *dev_priv;
+ bool ret = true;
+
+ spin_lock(&mchdev_lock);
+ if (!i915_mch_dev) {
+ ret = false;
+ goto out_unlock;
+ }
+ dev_priv = i915_mch_dev;
+
+ dev_priv->max_delay = dev_priv->fstart;
+
+ if (!ironlake_set_drps(dev_priv->dev, dev_priv->fstart))
+ ret = false;
+
+out_unlock:
+ spin_unlock(&mchdev_lock);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(i915_gpu_turbo_disable);
+
+/**
+ * Tells the intel_ips driver that the i915 driver is now loaded, if
+ * IPS got loaded first.
+ *
+ * This awkward dance is so that neither module has to depend on the
+ * other in order for IPS to do the appropriate communication of
+ * GPU turbo limits to i915.
+ */
+static void
+ips_ping_for_i915_load(void)
+{
+ void (*link)(void);
+
+ link = symbol_get(ips_link_to_i915_driver);
+ if (link) {
+ link();
+ symbol_put(ips_link_to_i915_driver);
+ }
+}
+
+void intel_gpu_ips_init(struct drm_i915_private *dev_priv)
+{
+ spin_lock(&mchdev_lock);
+ i915_mch_dev = dev_priv;
+ dev_priv->mchdev_lock = &mchdev_lock;
+ spin_unlock(&mchdev_lock);
+
+ ips_ping_for_i915_load();
+}
+
+void intel_gpu_ips_teardown(void)
+{
+ spin_lock(&mchdev_lock);
+ i915_mch_dev = NULL;
+ spin_unlock(&mchdev_lock);
+}
+
+void intel_init_emon(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 lcfuse;
+ u8 pxw[16];
+ int i;
+
+ /* Disable to program */
+ I915_WRITE(ECR, 0);
+ POSTING_READ(ECR);
+
+ /* Program energy weights for various events */
+ I915_WRITE(SDEW, 0x15040d00);
+ I915_WRITE(CSIEW0, 0x007f0000);
+ I915_WRITE(CSIEW1, 0x1e220004);
+ I915_WRITE(CSIEW2, 0x04000004);
+
+ for (i = 0; i < 5; i++)
+ I915_WRITE(PEW + (i * 4), 0);
+ for (i = 0; i < 3; i++)
+ I915_WRITE(DEW + (i * 4), 0);
+
+ /* Program P-state weights to account for frequency power adjustment */
+ for (i = 0; i < 16; i++) {
+ u32 pxvidfreq = I915_READ(PXVFREQ_BASE + (i * 4));
+ unsigned long freq = intel_pxfreq(pxvidfreq);
+ unsigned long vid = (pxvidfreq & PXVFREQ_PX_MASK) >>
+ PXVFREQ_PX_SHIFT;
+ unsigned long val;
+
+ val = vid * vid;
+ val *= (freq / 1000);
+ val *= 255;
+ val /= (127*127*900);
+ if (val > 0xff)
+ DRM_ERROR("bad pxval: %ld\n", val);
+ pxw[i] = val;
+ }
+ /* Render standby states get 0 weight */
+ pxw[14] = 0;
+ pxw[15] = 0;
+
+ for (i = 0; i < 4; i++) {
+ u32 val = (pxw[i*4] << 24) | (pxw[(i*4)+1] << 16) |
+ (pxw[(i*4)+2] << 8) | (pxw[(i*4)+3]);
+ I915_WRITE(PXW + (i * 4), val);
+ }
+
+ /* Adjust magic regs to magic values (more experimental results) */
+ I915_WRITE(OGW0, 0);
+ I915_WRITE(OGW1, 0);
+ I915_WRITE(EG0, 0x00007f00);
+ I915_WRITE(EG1, 0x0000000e);
+ I915_WRITE(EG2, 0x000e0000);
+ I915_WRITE(EG3, 0x68000300);
+ I915_WRITE(EG4, 0x42000000);
+ I915_WRITE(EG5, 0x00140031);
+ I915_WRITE(EG6, 0);
+ I915_WRITE(EG7, 0);
+
+ for (i = 0; i < 8; i++)
+ I915_WRITE(PXWL + (i * 4), 0);
+
+ /* Enable PMON + select events */
+ I915_WRITE(ECR, 0x80000019);
+
+ lcfuse = I915_READ(LCFUSE02);
+
+ dev_priv->corr = (lcfuse & LCFUSE_HIV_MASK);
+}
+
+static void ironlake_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ uint32_t dspclk_gate = VRHUNIT_CLOCK_GATE_DISABLE;
+
+ /* Required for FBC */
+ dspclk_gate |= DPFCUNIT_CLOCK_GATE_DISABLE |
+ DPFCRUNIT_CLOCK_GATE_DISABLE |
+ DPFDUNIT_CLOCK_GATE_DISABLE;
+ /* Required for CxSR */
+ dspclk_gate |= DPARBUNIT_CLOCK_GATE_DISABLE;
+
+ I915_WRITE(PCH_3DCGDIS0,
+ MARIUNIT_CLOCK_GATE_DISABLE |
+ SVSMUNIT_CLOCK_GATE_DISABLE);
+ I915_WRITE(PCH_3DCGDIS1,
+ VFMUNIT_CLOCK_GATE_DISABLE);
+
+ I915_WRITE(PCH_DSPCLK_GATE_D, dspclk_gate);
+
+ /*
+ * According to the spec the following bits should be set in
+ * order to enable memory self-refresh
+ * The bit 22/21 of 0x42004
+ * The bit 5 of 0x42020
+ * The bit 15 of 0x45000
+ */
+ I915_WRITE(ILK_DISPLAY_CHICKEN2,
+ (I915_READ(ILK_DISPLAY_CHICKEN2) |
+ ILK_DPARB_GATE | ILK_VSDPFD_FULL));
+ I915_WRITE(ILK_DSPCLK_GATE,
+ (I915_READ(ILK_DSPCLK_GATE) |
+ ILK_DPARB_CLK_GATE));
+ I915_WRITE(DISP_ARB_CTL,
+ (I915_READ(DISP_ARB_CTL) |
+ DISP_FBC_WM_DIS));
+ I915_WRITE(WM3_LP_ILK, 0);
+ I915_WRITE(WM2_LP_ILK, 0);
+ I915_WRITE(WM1_LP_ILK, 0);
+
+ /*
+ * Based on the document from hardware guys the following bits
+ * should be set unconditionally in order to enable FBC.
+ * The bit 22 of 0x42000
+ * The bit 22 of 0x42004
+ * The bit 7,8,9 of 0x42020.
+ */
+ if (IS_IRONLAKE_M(dev)) {
+ I915_WRITE(ILK_DISPLAY_CHICKEN1,
+ I915_READ(ILK_DISPLAY_CHICKEN1) |
+ ILK_FBCQ_DIS);
+ I915_WRITE(ILK_DISPLAY_CHICKEN2,
+ I915_READ(ILK_DISPLAY_CHICKEN2) |
+ ILK_DPARB_GATE);
+ I915_WRITE(ILK_DSPCLK_GATE,
+ I915_READ(ILK_DSPCLK_GATE) |
+ ILK_DPFC_DIS1 |
+ ILK_DPFC_DIS2 |
+ ILK_CLK_FBC);
+ }
+
+ I915_WRITE(ILK_DISPLAY_CHICKEN2,
+ I915_READ(ILK_DISPLAY_CHICKEN2) |
+ ILK_ELPIN_409_SELECT);
+ I915_WRITE(_3D_CHICKEN2,
+ _3D_CHICKEN2_WM_READ_PIPELINED << 16 |
+ _3D_CHICKEN2_WM_READ_PIPELINED);
+}
+
+static void gen6_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int pipe;
+ uint32_t dspclk_gate = VRHUNIT_CLOCK_GATE_DISABLE;
+
+ I915_WRITE(PCH_DSPCLK_GATE_D, dspclk_gate);
+
+ I915_WRITE(ILK_DISPLAY_CHICKEN2,
+ I915_READ(ILK_DISPLAY_CHICKEN2) |
+ ILK_ELPIN_409_SELECT);
+
+ I915_WRITE(WM3_LP_ILK, 0);
+ I915_WRITE(WM2_LP_ILK, 0);
+ I915_WRITE(WM1_LP_ILK, 0);
+
+ I915_WRITE(CACHE_MODE_0,
+ _MASKED_BIT_DISABLE(CM0_STC_EVICT_DISABLE_LRA_SNB));
+
+ I915_WRITE(GEN6_UCGCTL1,
+ I915_READ(GEN6_UCGCTL1) |
+ GEN6_BLBUNIT_CLOCK_GATE_DISABLE |
+ GEN6_CSUNIT_CLOCK_GATE_DISABLE);
+
+ /* According to the BSpec vol1g, bit 12 (RCPBUNIT) clock
+ * gating disable must be set. Failure to set it results in
+ * flickering pixels due to Z write ordering failures after
+ * some amount of runtime in the Mesa "fire" demo, and Unigine
+ * Sanctuary and Tropics, and apparently anything else with
+ * alpha test or pixel discard.
+ *
+ * According to the spec, bit 11 (RCCUNIT) must also be set,
+ * but we didn't debug actual testcases to find it out.
+ */
+ I915_WRITE(GEN6_UCGCTL2,
+ GEN6_RCPBUNIT_CLOCK_GATE_DISABLE |
+ GEN6_RCCUNIT_CLOCK_GATE_DISABLE);
+
+ /* Bspec says we need to always set all mask bits. */
+ I915_WRITE(_3D_CHICKEN, (0xFFFF << 16) |
+ _3D_CHICKEN_SF_DISABLE_FASTCLIP_CULL);
+
+ /*
+ * According to the spec the following bits should be
+ * set in order to enable memory self-refresh and fbc:
+ * The bit21 and bit22 of 0x42000
+ * The bit21 and bit22 of 0x42004
+ * The bit5 and bit7 of 0x42020
+ * The bit14 of 0x70180
+ * The bit14 of 0x71180
+ */
+ I915_WRITE(ILK_DISPLAY_CHICKEN1,
+ I915_READ(ILK_DISPLAY_CHICKEN1) |
+ ILK_FBCQ_DIS | ILK_PABSTRETCH_DIS);
+ I915_WRITE(ILK_DISPLAY_CHICKEN2,
+ I915_READ(ILK_DISPLAY_CHICKEN2) |
+ ILK_DPARB_GATE | ILK_VSDPFD_FULL);
+ I915_WRITE(ILK_DSPCLK_GATE,
+ I915_READ(ILK_DSPCLK_GATE) |
+ ILK_DPARB_CLK_GATE |
+ ILK_DPFD_CLK_GATE);
+
+ for_each_pipe(pipe) {
+ I915_WRITE(DSPCNTR(pipe),
+ I915_READ(DSPCNTR(pipe)) |
+ DISPPLANE_TRICKLE_FEED_DISABLE);
+ intel_flush_display_plane(dev_priv, pipe);
+ }
+}
+
+static void gen7_setup_fixed_func_scheduler(struct drm_i915_private *dev_priv)
+{
+ uint32_t reg = I915_READ(GEN7_FF_THREAD_MODE);
+
+ reg &= ~GEN7_FF_SCHED_MASK;
+ reg |= GEN7_FF_TS_SCHED_HW;
+ reg |= GEN7_FF_VS_SCHED_HW;
+ reg |= GEN7_FF_DS_SCHED_HW;
+
+ I915_WRITE(GEN7_FF_THREAD_MODE, reg);
+}
+
+static void ivybridge_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int pipe;
+ uint32_t dspclk_gate = VRHUNIT_CLOCK_GATE_DISABLE;
+ uint32_t snpcr;
+
+ I915_WRITE(PCH_DSPCLK_GATE_D, dspclk_gate);
+
+ I915_WRITE(WM3_LP_ILK, 0);
+ I915_WRITE(WM2_LP_ILK, 0);
+ I915_WRITE(WM1_LP_ILK, 0);
+
+ /* According to the spec, bit 13 (RCZUNIT) must be set on IVB.
+ * This implements the WaDisableRCZUnitClockGating workaround.
+ */
+ I915_WRITE(GEN6_UCGCTL2, GEN6_RCZUNIT_CLOCK_GATE_DISABLE);
+
+ I915_WRITE(ILK_DSPCLK_GATE, IVB_VRHUNIT_CLK_GATE);
+
+ I915_WRITE(IVB_CHICKEN3,
+ CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
+ CHICKEN3_DGMG_DONE_FIX_DISABLE);
+
+ /* Apply the WaDisableRHWOOptimizationForRenderHang workaround. */
+ I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1,
+ GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
+
+ /* WaApplyL3ControlAndL3ChickenMode requires those two on Ivy Bridge */
+ I915_WRITE(GEN7_L3CNTLREG1,
+ GEN7_WA_FOR_GEN7_L3_CONTROL);
+ I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER,
+ GEN7_WA_L3_CHICKEN_MODE);
+
+ /* This is required by WaCatErrorRejectionIssue */
+ I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
+ I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
+ GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
+
+ for_each_pipe(pipe) {
+ I915_WRITE(DSPCNTR(pipe),
+ I915_READ(DSPCNTR(pipe)) |
+ DISPPLANE_TRICKLE_FEED_DISABLE);
+ intel_flush_display_plane(dev_priv, pipe);
+ }
+
+ gen7_setup_fixed_func_scheduler(dev_priv);
+
+ /* WaDisable4x2SubspanOptimization */
+ I915_WRITE(CACHE_MODE_1,
+ _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
+
+ snpcr = I915_READ(GEN6_MBCUNIT_SNPCR);
+ snpcr &= ~GEN6_MBC_SNPCR_MASK;
+ snpcr |= GEN6_MBC_SNPCR_MED;
+ I915_WRITE(GEN6_MBCUNIT_SNPCR, snpcr);
+}
+
+static void valleyview_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int pipe;
+ uint32_t dspclk_gate = VRHUNIT_CLOCK_GATE_DISABLE;
+
+ I915_WRITE(PCH_DSPCLK_GATE_D, dspclk_gate);
+
+ I915_WRITE(WM3_LP_ILK, 0);
+ I915_WRITE(WM2_LP_ILK, 0);
+ I915_WRITE(WM1_LP_ILK, 0);
+
+ /* According to the spec, bit 13 (RCZUNIT) must be set on IVB.
+ * This implements the WaDisableRCZUnitClockGating workaround.
+ */
+ I915_WRITE(GEN6_UCGCTL2, GEN6_RCZUNIT_CLOCK_GATE_DISABLE);
+
+ I915_WRITE(ILK_DSPCLK_GATE, IVB_VRHUNIT_CLK_GATE);
+
+ I915_WRITE(IVB_CHICKEN3,
+ CHICKEN3_DGMG_REQ_OUT_FIX_DISABLE |
+ CHICKEN3_DGMG_DONE_FIX_DISABLE);
+
+ /* Apply the WaDisableRHWOOptimizationForRenderHang workaround. */
+ I915_WRITE(GEN7_COMMON_SLICE_CHICKEN1,
+ GEN7_CSC1_RHWO_OPT_DISABLE_IN_RCC);
+
+ /* WaApplyL3ControlAndL3ChickenMode requires those two on Ivy Bridge */
+ I915_WRITE(GEN7_L3CNTLREG1, GEN7_WA_FOR_GEN7_L3_CONTROL);
+ I915_WRITE(GEN7_L3_CHICKEN_MODE_REGISTER, GEN7_WA_L3_CHICKEN_MODE);
+
+ /* This is required by WaCatErrorRejectionIssue */
+ I915_WRITE(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG,
+ I915_READ(GEN7_SQ_CHICKEN_MBCUNIT_CONFIG) |
+ GEN7_SQ_CHICKEN_MBCUNIT_SQINTMOB);
+
+ for_each_pipe(pipe) {
+ I915_WRITE(DSPCNTR(pipe),
+ I915_READ(DSPCNTR(pipe)) |
+ DISPPLANE_TRICKLE_FEED_DISABLE);
+ intel_flush_display_plane(dev_priv, pipe);
+ }
+
+ I915_WRITE(CACHE_MODE_1,
+ _MASKED_BIT_ENABLE(PIXEL_SUBSPAN_COLLECT_OPT_DISABLE));
+}
+
+static void g4x_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ uint32_t dspclk_gate;
+
+ I915_WRITE(RENCLK_GATE_D1, 0);
+ I915_WRITE(RENCLK_GATE_D2, VF_UNIT_CLOCK_GATE_DISABLE |
+ GS_UNIT_CLOCK_GATE_DISABLE |
+ CL_UNIT_CLOCK_GATE_DISABLE);
+ I915_WRITE(RAMCLK_GATE_D, 0);
+ dspclk_gate = VRHUNIT_CLOCK_GATE_DISABLE |
+ OVRUNIT_CLOCK_GATE_DISABLE |
+ OVCUNIT_CLOCK_GATE_DISABLE;
+ if (IS_GM45(dev))
+ dspclk_gate |= DSSUNIT_CLOCK_GATE_DISABLE;
+ I915_WRITE(DSPCLK_GATE_D, dspclk_gate);
+}
+
+static void crestline_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ I915_WRITE(RENCLK_GATE_D1, I965_RCC_CLOCK_GATE_DISABLE);
+ I915_WRITE(RENCLK_GATE_D2, 0);
+ I915_WRITE(DSPCLK_GATE_D, 0);
+ I915_WRITE(RAMCLK_GATE_D, 0);
+ I915_WRITE16(DEUC, 0);
+}
+
+static void broadwater_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ I915_WRITE(RENCLK_GATE_D1, I965_RCZ_CLOCK_GATE_DISABLE |
+ I965_RCC_CLOCK_GATE_DISABLE |
+ I965_RCPB_CLOCK_GATE_DISABLE |
+ I965_ISC_CLOCK_GATE_DISABLE |
+ I965_FBC_CLOCK_GATE_DISABLE);
+ I915_WRITE(RENCLK_GATE_D2, 0);
+}
+
+static void gen3_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 dstate = I915_READ(D_STATE);
+
+ dstate |= DSTATE_PLL_D3_OFF | DSTATE_GFX_CLOCK_GATING |
+ DSTATE_DOT_CLOCK_GATING;
+ I915_WRITE(D_STATE, dstate);
+
+ if (IS_PINEVIEW(dev))
+ I915_WRITE(ECOSKPD, _MASKED_BIT_ENABLE(ECO_GATING_CX_ONLY));
+}
+
+static void i85x_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ I915_WRITE(RENCLK_GATE_D1, SV_CLOCK_GATE_DISABLE);
+}
+
+static void i830_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ I915_WRITE(DSPCLK_GATE_D, OVRUNIT_CLOCK_GATE_DISABLE);
+}
+
+static void ibx_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ /*
+ * On Ibex Peak and Cougar Point, we need to disable clock
+ * gating for the panel power sequencer or it will fail to
+ * start up when no ports are active.
+ */
+ I915_WRITE(SOUTH_DSPCLK_GATE_D, PCH_DPLSUNIT_CLOCK_GATE_DISABLE);
+}
+
+static void cpt_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int pipe;
+
+ /*
+ * On Ibex Peak and Cougar Point, we need to disable clock
+ * gating for the panel power sequencer or it will fail to
+ * start up when no ports are active.
+ */
+ I915_WRITE(SOUTH_DSPCLK_GATE_D, PCH_DPLSUNIT_CLOCK_GATE_DISABLE);
+ I915_WRITE(SOUTH_CHICKEN2, I915_READ(SOUTH_CHICKEN2) |
+ DPLS_EDP_PPS_FIX_DIS);
+ /* Without this, mode sets may fail silently on FDI */
+ for_each_pipe(pipe)
+ I915_WRITE(TRANS_CHICKEN2(pipe), TRANS_AUTOTRAIN_GEN_STALL_DIS);
+}
+
+void intel_init_clock_gating(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ dev_priv->display.init_clock_gating(dev);
+
+ if (dev_priv->display.init_pch_clock_gating)
+ dev_priv->display.init_pch_clock_gating(dev);
+}
+
+static void gen6_sanitize_pm(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ u32 limits, delay, old;
+
+ gen6_gt_force_wake_get(dev_priv);
+
+ old = limits = I915_READ(GEN6_RP_INTERRUPT_LIMITS);
+ /* Make sure we continue to get interrupts
+ * until we hit the minimum or maximum frequencies.
+ */
+ limits &= ~(0x3f << 16 | 0x3f << 24);
+ delay = dev_priv->cur_delay;
+ if (delay < dev_priv->max_delay)
+ limits |= (dev_priv->max_delay & 0x3f) << 24;
+ if (delay > dev_priv->min_delay)
+ limits |= (dev_priv->min_delay & 0x3f) << 16;
+
+ if (old != limits) {
+ /* Note that the known failure case is to read back 0. */
+ DRM_DEBUG_DRIVER("Power management discrepancy: GEN6_RP_INTERRUPT_LIMITS "
+ "expected %08x, was %08x\n", limits, old);
+ I915_WRITE(GEN6_RP_INTERRUPT_LIMITS, limits);
+ }
+
+ gen6_gt_force_wake_put(dev_priv);
+}
+
+void intel_sanitize_pm(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ if (dev_priv->display.sanitize_pm)
+ dev_priv->display.sanitize_pm(dev);
+}
+
+/* Starting with Haswell, we have different power wells for
+ * different parts of the GPU. This attempts to enable them all.
+ */
+void intel_init_power_wells(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ unsigned long power_wells[] = {
+ HSW_PWR_WELL_CTL1,
+ HSW_PWR_WELL_CTL2,
+ HSW_PWR_WELL_CTL4
+ };
+ int i;
+
+ if (!IS_HASWELL(dev))
+ return;
+
+ mutex_lock(&dev->struct_mutex);
+
+ for (i = 0; i < ARRAY_SIZE(power_wells); i++) {
+ int well = I915_READ(power_wells[i]);
+
+ if ((well & HSW_PWR_WELL_STATE) == 0) {
+ I915_WRITE(power_wells[i], well & HSW_PWR_WELL_ENABLE);
+ if (wait_for(I915_READ(power_wells[i] & HSW_PWR_WELL_STATE), 20))
+ DRM_ERROR("Error enabling power well %lx\n", power_wells[i]);
+ }
+ }
+
+ mutex_unlock(&dev->struct_mutex);
+}
+
+/* Set up chip specific power management-related functions */
+void intel_init_pm(struct drm_device *dev)
+{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+
+ if (I915_HAS_FBC(dev)) {
+ if (HAS_PCH_SPLIT(dev)) {
+ dev_priv->display.fbc_enabled = ironlake_fbc_enabled;
+ dev_priv->display.enable_fbc = ironlake_enable_fbc;
+ dev_priv->display.disable_fbc = ironlake_disable_fbc;
+ } else if (IS_GM45(dev)) {
+ dev_priv->display.fbc_enabled = g4x_fbc_enabled;
+ dev_priv->display.enable_fbc = g4x_enable_fbc;
+ dev_priv->display.disable_fbc = g4x_disable_fbc;
+ } else if (IS_CRESTLINE(dev)) {
+ dev_priv->display.fbc_enabled = i8xx_fbc_enabled;
+ dev_priv->display.enable_fbc = i8xx_enable_fbc;
+ dev_priv->display.disable_fbc = i8xx_disable_fbc;
+ }
+ /* 855GM needs testing */
+ }
+
+ /* For cxsr */
+ if (IS_PINEVIEW(dev))
+ i915_pineview_get_mem_freq(dev);
+ else if (IS_GEN5(dev))
+ i915_ironlake_get_mem_freq(dev);
+
+ /* For FIFO watermark updates */
+ if (HAS_PCH_SPLIT(dev)) {
+ dev_priv->display.force_wake_get = __gen6_gt_force_wake_get;
+ dev_priv->display.force_wake_put = __gen6_gt_force_wake_put;
+
+ /* IVB configs may use multi-threaded forcewake */
+ if (IS_IVYBRIDGE(dev) || IS_HASWELL(dev)) {
+ u32 ecobus;
+
+ /* A small trick here - if the bios hasn't configured MT forcewake,
+ * and if the device is in RC6, then force_wake_mt_get will not wake
+ * the device and the ECOBUS read will return zero. Which will be
+ * (correctly) interpreted by the test below as MT forcewake being
+ * disabled.
+ */
+ mutex_lock(&dev->struct_mutex);
+ __gen6_gt_force_wake_mt_get(dev_priv);
+ ecobus = I915_READ_NOTRACE(ECOBUS);
+ __gen6_gt_force_wake_mt_put(dev_priv);
+ mutex_unlock(&dev->struct_mutex);
+
+ if (ecobus & FORCEWAKE_MT_ENABLE) {
+ DRM_DEBUG_KMS("Using MT version of forcewake\n");
+ dev_priv->display.force_wake_get =
+ __gen6_gt_force_wake_mt_get;
+ dev_priv->display.force_wake_put =
+ __gen6_gt_force_wake_mt_put;
+ }
+ }
+
+ if (HAS_PCH_IBX(dev))
+ dev_priv->display.init_pch_clock_gating = ibx_init_clock_gating;
+ else if (HAS_PCH_CPT(dev))
+ dev_priv->display.init_pch_clock_gating = cpt_init_clock_gating;
+
+ if (IS_GEN5(dev)) {
+ if (I915_READ(MLTR_ILK) & ILK_SRLT_MASK)
+ dev_priv->display.update_wm = ironlake_update_wm;
+ else {
+ DRM_DEBUG_KMS("Failed to get proper latency. "
+ "Disable CxSR\n");
+ dev_priv->display.update_wm = NULL;
+ }
+ dev_priv->display.init_clock_gating = ironlake_init_clock_gating;
+ } else if (IS_GEN6(dev)) {
+ if (SNB_READ_WM0_LATENCY()) {
+ dev_priv->display.update_wm = sandybridge_update_wm;
+ dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
+ } else {
+ DRM_DEBUG_KMS("Failed to read display plane latency. "
+ "Disable CxSR\n");
+ dev_priv->display.update_wm = NULL;
+ }
+ dev_priv->display.init_clock_gating = gen6_init_clock_gating;
+ dev_priv->display.sanitize_pm = gen6_sanitize_pm;
+ } else if (IS_IVYBRIDGE(dev)) {
+ /* FIXME: detect B0+ stepping and use auto training */
+ if (SNB_READ_WM0_LATENCY()) {
+ dev_priv->display.update_wm = sandybridge_update_wm;
+ dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
+ } else {
+ DRM_DEBUG_KMS("Failed to read display plane latency. "
+ "Disable CxSR\n");
+ dev_priv->display.update_wm = NULL;
+ }
+ dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
+ dev_priv->display.sanitize_pm = gen6_sanitize_pm;
+ } else if (IS_HASWELL(dev)) {
+ if (SNB_READ_WM0_LATENCY()) {
+ dev_priv->display.update_wm = sandybridge_update_wm;
+ dev_priv->display.update_sprite_wm = sandybridge_update_sprite_wm;
+ dev_priv->display.update_linetime_wm = haswell_update_linetime_wm;
+ } else {
+ DRM_DEBUG_KMS("Failed to read display plane latency. "
+ "Disable CxSR\n");
+ dev_priv->display.update_wm = NULL;
+ }
+ dev_priv->display.init_clock_gating = ivybridge_init_clock_gating;
+ dev_priv->display.sanitize_pm = gen6_sanitize_pm;
+ } else
+ dev_priv->display.update_wm = NULL;
+ } else if (IS_VALLEYVIEW(dev)) {
+ dev_priv->display.update_wm = valleyview_update_wm;
+ dev_priv->display.init_clock_gating =
+ valleyview_init_clock_gating;
+ dev_priv->display.force_wake_get = vlv_force_wake_get;
+ dev_priv->display.force_wake_put = vlv_force_wake_put;
+ } else if (IS_PINEVIEW(dev)) {
+ if (!intel_get_cxsr_latency(IS_PINEVIEW_G(dev),
+ dev_priv->is_ddr3,
+ dev_priv->fsb_freq,
+ dev_priv->mem_freq)) {
+ DRM_INFO("failed to find known CxSR latency "
+ "(found ddr%s fsb freq %d, mem freq %d), "
+ "disabling CxSR\n",
+ (dev_priv->is_ddr3 == 1) ? "3" : "2",
+ dev_priv->fsb_freq, dev_priv->mem_freq);
+ /* Disable CxSR and never update its watermark again */
+ pineview_disable_cxsr(dev);
+ dev_priv->display.update_wm = NULL;
+ } else
+ dev_priv->display.update_wm = pineview_update_wm;
+ dev_priv->display.init_clock_gating = gen3_init_clock_gating;
+ } else if (IS_G4X(dev)) {
+ dev_priv->display.update_wm = g4x_update_wm;
+ dev_priv->display.init_clock_gating = g4x_init_clock_gating;
+ } else if (IS_GEN4(dev)) {
+ dev_priv->display.update_wm = i965_update_wm;
+ if (IS_CRESTLINE(dev))
+ dev_priv->display.init_clock_gating = crestline_init_clock_gating;
+ else if (IS_BROADWATER(dev))
+ dev_priv->display.init_clock_gating = broadwater_init_clock_gating;
+ } else if (IS_GEN3(dev)) {
+ dev_priv->display.update_wm = i9xx_update_wm;
+ dev_priv->display.get_fifo_size = i9xx_get_fifo_size;
+ dev_priv->display.init_clock_gating = gen3_init_clock_gating;
+ } else if (IS_I865G(dev)) {
+ dev_priv->display.update_wm = i830_update_wm;
+ dev_priv->display.init_clock_gating = i85x_init_clock_gating;
+ dev_priv->display.get_fifo_size = i830_get_fifo_size;
+ } else if (IS_I85X(dev)) {
+ dev_priv->display.update_wm = i9xx_update_wm;
+ dev_priv->display.get_fifo_size = i85x_get_fifo_size;
+ dev_priv->display.init_clock_gating = i85x_init_clock_gating;
+ } else {
+ dev_priv->display.update_wm = i830_update_wm;
+ dev_priv->display.init_clock_gating = i830_init_clock_gating;
+ if (IS_845G(dev))
+ dev_priv->display.get_fifo_size = i845_get_fifo_size;
+ else
+ dev_priv->display.get_fifo_size = i830_get_fifo_size;
+ }
+
+ /* We attempt to init the necessary power wells early in the initialization
+ * time, so the subsystems that expect power to be enabled can work.
+ */
+ intel_init_power_wells(dev);
+}
+